search

ankushgarg1998 / ipu-ranklist

:chart_with_upwards_trend: A minimalist result & ranklist application for IP University (GGSIPU) folks. All results starting 2015.
https://ipuranklist.com/
116 stars 15 forks source link

Personal updates on release of results #149

Open rajatmw1999 opened 1 year ago

rajatmw1999 commented 1 year ago

@ankushgarg1998 Opening this issue, if you feel it is a good addition, please do let me know, I will create a POC and present it for further development. I would like to contribute to this project, so will handle things in this feature if required.

ankushgarg1998 commented 1 year ago

Hi @rajatmw1999 This is a good idea overall. But there's a lot to solutionize before implementing it.

  1. How do we get the email IDs/contact of students?
  2. There's a lot of noise on the IPU's results page (Supplementary results, Reappear results, Technical glitch), how do we identify & stop alerts from these pages?
  3. How do we identify which emails to alert if the result announced is for a specific program (say B. Com.)?

Right now, the PDF upload process is manual. This will add to the manual effort. I'm planning to create an automated version of the results PDF parser. Shall pick this after that. Let me know if you'd like me to include you then.

rajatmw1999 commented 1 year ago

Hi @ankushgarg1998 Appreciate you taking the time to reply. Here are my suggestions.

  1. Students can signup themselves for these updates. We will provide a call to action on the homepage and result page that draws attention and users who like can signup for these updates. I believe people who want to get such news first before anyone else will want to sign up
  2. I believe they all will have particular names in their PDFs. I understand reading PDF names is not a solid logical solution but where's the fun in easy? We can find some ways of either reading the pdf names or reading the first new pages and identifying the year/type of result. Lots of thrid party libraries to read these things and extract meaningful information. It will be hard work though, no denying
  3. Same as point 2. We read PDF names and we read the contens of first few pages.

I will be excited to work on this automated feature. Sign me up! You might already have my whatsapp, if not please let me know, I will send a 'Hi' and we can setup meetings to talk on this further.

ankushgarg1998 commented 1 year ago

Hi @rajatmw1999 Thanks for elaborating on the approach you had in mind.

Wouldn't say it's concrete, but something along these lines is feasible.

I don't think I have your number. Please send me a "Hi" on WhatsApp. I'll loop you in whenever I plan to pick this up. Would be a fun problem to solve.